DACOM: Learning Delay-Aware Communication for Multi-Agent Reinforcement Learning

2022-12-03 · Tingting Yuan, Hwei-Ming Chung, Jie Yuan, XiaoMing Fu

Communication is supposed to improve multi-agent collaboration and overall performance in cooperative Multi-agent reinforcement learning (MARL). However, such improvements are prevalently limited in practice since most existing communication schemes ignore communication overheads (e.g., communication delays). In this paper, we demonstrate that ignoring communication delays has detrimental effects on collaborations, especially in delay-sensitive tasks such as autonomous driving. To mitigate this impact, we design a delay-aware multi-agent communication model (DACOM) to adapt communication to delays. Specifically, DACOM introduces a component, TimeNet, that is responsible for adjusting the waiting time of an agent to receive messages from other agents such that the uncertainty associated with delay can be addressed. Our experiments reveal that DACOM has a non-negligible performance improvement over other mechanisms by making a better trade-off between the benefits of communication and the costs of waiting for messages.

📄 PDF Abstract BibTeX arXiv:2212.01619

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD

2018-10-19 · Jianyu Wang, Gauri Joshi

Large-scale machine learning training, in particular distributed stochastic gradient descent, needs to be robust to inherent system variability such as node straggling and random communication delays. This work considers…

Delay-Aware Multi-Agent Reinforcement Learning for Cooperative and Competitive Environments

2020-05-11 · Baiming Chen, Mengdi Xu, Zuxin Liu, Liang Li 외

Action and observation delays exist prevalently in the real-world cyber-physical systems which may pose challenges in reinforcement learning design. It is particularly an arduous task when handling multi-agent systems wh…

Autonomous Vehicles Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning+2

DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle

2025-12-03 · Fangyu Lei, Jinxiang Meng, Yiming Huang, Junjie Zhao 외 arxiv

Real-world enterprise data intelligence workflows encompass data engineering that turns raw sources into analytical-ready tables and data analysis that convert those tables into decision-oriented insights. We introduce D…

Code Generation

Learning Agent-Compatible Context Management for Long-Horizon Tasks

2026-05-29 · Lu Yi, Runlin Lei, Liuyi Yao, Yuexiang Xie 외 arxiv

LLM agents increasingly face long-horizon tasks such as web search and deep research in real-world applications, where accumulated context can cause long-context degradation and reasoning failures. Prior work mitigates t…

Reinforcement Learning

AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training

2017-12-07 · Chia-Yu Chen, Jungwook Choi, Daniel Brand, Ankur Agrawal 외

Highly distributed training of Deep Neural Networks (DNNs) on future compute platforms (offering 100 of TeraOps/s of computational capacity) is expected to be severely communication constrained. To overcome this limitati…

Quantization